INDEX

Explanations

lines of code and programming constructs related to functionality and configuration

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 فريبيس

-0.87

 tslint

-0.83

 للمعارف

-0.81

 الدولى

-0.77

脚注の使い方

-0.75

 NDEBUG

-0.69

 BoxDecoration

-0.68

 OnDestroy

-0.67

-------

-0.66

✭✭

-0.65

POSITIVE LOGITS

0.57

0.51

0.46

LookAnd

0.44

op

0.43

repar

0.43

是大

0.43

name

0.42

Activations Density 0.574%

lines of code and programming constructs related to functionality and configuration

No Comments

No Known Activations